INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

mentions of people's names

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pmwiki

-0.70

 Soviets

-0.69

 rumored

-0.68

ãĢı

-0.67

othal

-0.66

 incor

-0.64

 scen

-0.64

direction

-0.64

 Communists

-0.63

ĺħ

-0.63

POSITIVE LOGITS

 Becker

0.98

 Peters

0.96

 Cumm

0.95

Wol

0.94

 Murphy

0.92

 Nichols

0.90

 Hansen

0.89

 Walsh

0.89

 Martinez

0.88

 Nicol

0.88

Activations Density 0.250%

names of individuals

mentions of people's names

No Comments

No Known Activations